Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Euro
    -0.07
     май
    -0.07
     Repair
    -0.07
     Error
    -0.07
     niž
    -0.07
     salvage
    -0.07
    نامه
    -0.06
    izont
    -0.06
    liž
    -0.06
    ised
    -0.06
    POSITIVE LOGITS
     both
    0.20
     Both
    0.17
    Both
    0.16
    both
    0.15
     BOTH
    0.12
     booth
    0.08
     all
    0.08
    :both
    0.07
     ambos
    0.07
     each
    0.07
    Act Density 0.046%

    No Known Activations